Lorenzo Bardone

3 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

ICML (2) NeurIPS (1)

Top co-authors

Sebastian Goldt (3) Federica Gerace (1) Fabiola Ricci (1) Eszter Székely (1)

Research topics

Deep Learning (3) Machine Learning (3) Architectures (3) Optimization & Theory · Machine Learning (3) Core Methods (2) Mathematics & Optimization (1) Learning Types (1) Mathematics (1) Optimization & Theory · Deep Learning (1)

Keywords

sample complexity (3) higher-order cumulant (2) stochastic gradient descent (2) computational complexity (1) latent variable (1) random feature (1) statistical limit (1) neural network (1) online sgd (1) spiked cumulant model (1) imagenet (1) correlation (1) fastica (1) statistical learning (1) non-gaussianity (1) feature learning (1) independent component analysis (1)

Papers

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions ICML 2025 Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks NeurIPS 2024 Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks ICML 2024